Deep Joint Entity Disambiguation with Local Neural Attention

Ganea, Octavian-Eugen; Hofmann, Thomas

doi:10.18653/v1/d17-1277

Cited by 256 publications

(293 citation statements)

References 21 publications

Supporting

Mentioning

292

Contrasting

Order By: Relevance

“…Later, some work [11,12] proposed to convert mentions and candidate entities into a common vector space, and then disambiguated candidate entities by a scoring function (e.g., cosine similarity). In recent years, neural network-based approaches have shown considerable success in entity normalization [13][14][15]. These methods used neural architectures to learn the context representations around an entity mention and calculated the context-entity similarity scores to determine which candidate is a correct assignment.…”

Section: Introductionmentioning

confidence: 99%

Knowledge-enhanced biomedical named entity recognition and normalization: application to proteins and genes

et al. 2020

View full text Add to dashboard Cite

Background: Automated biomedical named entity recognition and normalization serves as the basis for many downstream applications in information management. However, this task is challenging due to name variations and entity ambiguity. A biomedical entity may have multiple variants and a variant could denote several different entity identifiers. Results: To remedy the above issues, we present a novel knowledge-enhanced system for protein/gene named entity recognition (PNER) and normalization (PNEN). On one hand, a large amount of entity name knowledge extracted from biomedical knowledge bases is used to recognize more entity variants. On the other hand, structural knowledge of entities is extracted and encoded as identifier (ID) embeddings, which are then used for better entity normalization. Moreover, deep contextualized word representations generated by pre-trained language models are also incorporated into our knowledge-enhanced system for modeling multi-sense information of entities. Experimental results on the BioCreative VI Bio-ID corpus show that our proposed knowledge-enhanced system achieves 0.871 F1-score for PNER and 0.445 F1-score for PNEN, respectively, leading to a new state-of-the-art performance. Conclusions: We propose a knowledge-enhanced system that combines both entity knowledge and deep contextualized word representations. Comparison results show that entity knowledge is beneficial to the PNER and PNEN task and can be well combined with contextualized information in our system for further improvement.

show abstract

Section: Introductionmentioning

confidence: 99%

Knowledge-enhanced biomedical named entity recognition and normalization: application to proteins and genes

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A KGQA system as in Section 2.2 collects candidate answers. A corpus search collects snippets from top-ranking documents and annotates (Globerson et al, 2016;Ganea and Hofmann, 2017) them with KG entities. For each candidate in the union, features are collected from both KG and corpus snippets to rank them.…”

Section: Combining Corpus and Kgmentioning

confidence: 99%

Neural architecture for question answering using a knowledge graph and web corpus

et al. 2019

View full text Add to dashboard Cite

In Web search, entity-seeking queries often trigger a special Question Answering (QA) system. It may use a parser to interpret the question to a structured query, execute that on a knowledge graph (KG), and return direct entity responses. QA systems based on precise parsing tend to be brittle: minor syntax variations may dramatically change the response. Moreover, KG coverage is patchy. At the other extreme, a large corpus may provide broader coverage, but in an unstructured, unreliable form. We present AQQUCN, a QA system that gracefully combines KG and corpus evidence. AQQUCN accepts a broad spectrum of query syntax, between well-formed questions to short "telegraphic" keyword sequences. In the face of inherent query ambiguities, AQQUCN aggregates signals from KGs and large corpora to directly rank KG entities, rather than commit to one semantic interpretation of the query. AQQUCN models the ideal interpretation as an unobservable or latent variable. Interpretations and candidate entity responses are scored as pairs, by combining signals from multiple convolutional networks that operate collectively on the query, KG and corpus. On four public query workloads, amounting to over 8,000 queries with diverse query syntax, we see 5-16% absolute improvement in mean average precision (MAP), compared to the entity ranking performance of recent systems. Our system is also competitive at entity set retrieval, almost doubling F1 scores for challenging short queries.

show abstract

“…However, Sun [1] argues that these methods are insufficient to disentangle the underlying explanatory factors of the data and proposes a method which employs a convolutional neural network (CNN) to encode the entity description. Some other methods [3,[7][8][9] try to encode the entity, based on the idea of word embedding, which only takes entity context into consideration. However, all the methods above fail to capture different information aspects of entity, which could result in a loss of information.…”

Section: Introductionmentioning

confidence: 99%

“…The semantics of mention mainly come from the mention context and other mentions in the given document. For mention context, most previous methods assume that all the words in the context have the same importance [1,4,6,8,12]. Obviously, this should be investigated carefully.…”

Section: Introductionmentioning

confidence: 99%

“…Obviously, this should be investigated carefully. Some works [8,13] try to introduce the standard attention mechanism to fix this problem. However, the standard attention mechanism can be viewed as a process of performing soft selections of individual words independently; it ignores the dependencies between words, and may make mistakes when complex expressions are involved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention-Based Joint Entity Linking with Entity Embedding

Liu

Sun

et al. 2019

Information

View full text Add to dashboard Cite

Entity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context, and modeling the coherence among mentions. For the encoding of entity, we use long short term memory (LSTM) and a convolutional neural network (CNN) to encode the entity context and entity description, respectively. Then, we design a function to combine all the different entity information aspects, in order to generate unified, dense entity embeddings. For the encoding of mention context, unlike standard attention mechanisms which can only capture important individual words, we introduce a novel, attention mechanism-based LSTM model, which can effectively capture the important text spans around a given mention with a conditional random field (CRF) layer. In addition, we take the coherence among mentions into consideration with a Forward-Backward Algorithm, which is less time-consuming than previous methods. Our experimental results show that our model obtains a competitive, or even better, performance than state-of-the-art models across different datasets.

show abstract

Deep Joint Entity Disambiguation with Local Neural Attention

Cited by 256 publications

References 21 publications

Knowledge-enhanced biomedical named entity recognition and normalization: application to proteins and genes

Knowledge-enhanced biomedical named entity recognition and normalization: application to proteins and genes

Neural architecture for question answering using a knowledge graph and web corpus

Attention-Based Joint Entity Linking with Entity Embedding

Contact Info

Product

Resources

About